Update for build.toml changes

Browse files

Files changed (16) hide show

build.toml +10 -12
flake.lock +0 -95
{ext-torch → torch-ext}/quantization/__init__.py +0 -0
{ext-torch → torch-ext}/quantization/compressed_tensors.py +0 -0
{ext-torch → torch-ext}/quantization/cutlass.py +0 -0
{ext-torch → torch-ext}/quantization/marlin.py +0 -0
{ext-torch → torch-ext}/quantization/scalar_type.py +0 -0
{ext-torch → torch-ext}/quantization/utils/__init__.py +0 -0
{ext-torch → torch-ext}/quantization/utils/marlin_utils.py +0 -0
{ext-torch → torch-ext}/quantization/utils/marlin_utils_fp8.py +0 -0
{ext-torch → torch-ext}/quantization/utils/marlin_utils_test.py +0 -0
{ext-torch → torch-ext}/quantization/utils/marlin_utils_test_24.py +0 -0
{ext-torch → torch-ext}/quantization/utils/marlin_utils_test_qqq.py +0 -0
{ext-torch → torch-ext}/quantization/utils/quant_utils.py +0 -0
{ext-torch → torch-ext}/torch_binding.cpp +0 -0
{ext-torch → torch-ext}/torch_binding.h +0 -0

build.toml CHANGED Viewed

@@ -1,19 +1,17 @@
 [general]
-version = "0.0.1"
 [torch]
-name = "quantization"
 src = [
   "core/registration.h",
   "core/scalar_type.hpp",
-  "ext-torch/torch_binding.cpp",
-  "ext-torch/torch_binding.h"
 ]
 include = [ "." ]
-pyroot = "ext-torch"
 [kernel.cutlass_w8a8]
-capabilities = [ "7.5", "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "core/math.hpp",
   "cutlass_w8a8/common.hpp",
@@ -31,7 +29,7 @@ include = [ "." ]
 depends = [ "cutlass_3_6", "torch" ]
 [kernel.cutlass_w8a8_hopper]
-capabilities = [ "9.0", "9.0a" ]
 src = [
   "core/math.hpp",
   "cutlass_w8a8/common.hpp",
@@ -48,7 +46,7 @@ include = [ "." ]
 depends = [ "cutlass_3_6", "torch" ]
 [kernel.fp8_common]
-capabilities = [ "7.5", "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "fp8/common.cu",
   "fp8/common.cuh",
@@ -59,7 +57,7 @@ include = [ "." ]
 depends = [ "torch" ]
 [kernel.fp8_marlin]
-capabilities = [ "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "fp8/fp8_marlin.cu",
   "gptq_marlin/marlin.cuh",
@@ -68,7 +66,7 @@ src = [
 depends = [ "torch" ]
 [kernel.int8_common]
-capabilities = [ "7.5", "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "compressed_tensors/int8_quant_kernels.cu",
   "dispatch_utils.h"
@@ -77,7 +75,7 @@ include = [ "." ]
 depends = [ "torch" ]
 [kernel.gptq_marlin]
-capabilities = [ "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "core/scalar_type.hpp",
   "gptq_marlin/awq_marlin_repack.cu",
@@ -90,7 +88,7 @@ include = [ "." ]
 depends = [ "torch" ]
 [kernel.marlin]
-capabilities = [ "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "core/scalar_type.hpp",
   "marlin/dense/common/base.h",

 [general]
+name = "quantization"
 [torch]
 src = [
   "core/registration.h",
   "core/scalar_type.hpp",
+  "torch-ext/torch_binding.cpp",
+  "torch-ext/torch_binding.h"
 ]
 include = [ "." ]
 [kernel.cutlass_w8a8]
+cuda-capabilities = [ "7.5", "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "core/math.hpp",
   "cutlass_w8a8/common.hpp",
 depends = [ "cutlass_3_6", "torch" ]
 [kernel.cutlass_w8a8_hopper]
+cuda-capabilities = [ "9.0", "9.0a" ]
 src = [
   "core/math.hpp",
   "cutlass_w8a8/common.hpp",
 depends = [ "cutlass_3_6", "torch" ]
 [kernel.fp8_common]
+cuda-capabilities = [ "7.5", "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "fp8/common.cu",
   "fp8/common.cuh",
 depends = [ "torch" ]
 [kernel.fp8_marlin]
+cuda-capabilities = [ "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "fp8/fp8_marlin.cu",
   "gptq_marlin/marlin.cuh",
 depends = [ "torch" ]
 [kernel.int8_common]
+cuda-capabilities = [ "7.5", "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "compressed_tensors/int8_quant_kernels.cu",
   "dispatch_utils.h"
 depends = [ "torch" ]
 [kernel.gptq_marlin]
+cuda-capabilities = [ "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "core/scalar_type.hpp",
   "gptq_marlin/awq_marlin_repack.cu",
 depends = [ "torch" ]
 [kernel.marlin]
+cuda-capabilities = [ "8.0", "8.6", "8.7", "8.9", "9.0", "9.0a" ]
 src = [
   "core/scalar_type.hpp",
   "marlin/dense/common/base.h",

flake.lock DELETED Viewed

@@ -1,95 +0,0 @@
-{
-  "nodes": {
-    "flake-compat": {
-      "locked": {
-        "lastModified": 1732722421,
-        "narHash": "sha256-HRJ/18p+WoXpWJkcdsk9St5ZiukCqSDgbOGFa8Okehg=",
-        "owner": "edolstra",
-        "repo": "flake-compat",
-        "rev": "9ed2ac151eada2306ca8c418ebd97807bb08f6ac",
-        "type": "github"
-      },
-      "original": {
-        "owner": "edolstra",
-        "repo": "flake-compat",
-        "type": "github"
-      }
-    },
-    "flake-utils": {
-      "inputs": {
-        "systems": "systems"
-      },
-      "locked": {
-        "lastModified": 1731533236,
-        "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
-        "type": "github"
-      },
-      "original": {
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "type": "github"
-      }
-    },
-    "kernel-builder": {
-      "inputs": {
-        "flake-compat": "flake-compat",
-        "flake-utils": "flake-utils",
-        "nixpkgs": "nixpkgs"
-      },
-      "locked": {
-        "lastModified": 1737048117,
-        "narHash": "sha256-WEsPsP3RU2XdUWSm5i23gonDxitA/IwxsroMX0OowTw=",
-        "ref": "refs/heads/main",
-        "rev": "9767f35a39472900a0957b2b028da9068431e53f",
-        "revCount": 71,
-        "type": "git",
-        "url": "ssh://git@github.com/huggingface/kernel-builder"
-      },
-      "original": {
-        "type": "git",
-        "url": "ssh://git@github.com/huggingface/kernel-builder"
-      }
-    },
-    "nixpkgs": {
-      "locked": {
-        "lastModified": 1732866476,
-        "narHash": "sha256-fQPhGk0rBifqOtcq07Que6MWuWU08AmiaOVZ6TTAHUw=",
-        "owner": "nixos",
-        "repo": "nixpkgs",
-        "rev": "564e219aa5ca9306ab22fb803c16391aacb4417b",
-        "type": "github"
-      },
-      "original": {
-        "owner": "nixos",
-        "ref": "nixos-unstable-small",
-        "repo": "nixpkgs",
-        "type": "github"
-      }
-    },
-    "root": {
-      "inputs": {
-        "kernel-builder": "kernel-builder"
-      }
-    },
-    "systems": {
-      "locked": {
-        "lastModified": 1681028828,
-        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
-        "owner": "nix-systems",
-        "repo": "default",
-        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
-        "type": "github"
-      },
-      "original": {
-        "owner": "nix-systems",
-        "repo": "default",
-        "type": "github"
-      }
-    }
-  },
-  "root": "root",
-  "version": 7
-}

{ext-torch → torch-ext}/quantization/__init__.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/compressed_tensors.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/cutlass.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/marlin.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/scalar_type.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/utils/__init__.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/utils/marlin_utils.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/utils/marlin_utils_fp8.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/utils/marlin_utils_test.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/utils/marlin_utils_test_24.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/utils/marlin_utils_test_qqq.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/quantization/utils/quant_utils.py RENAMED Viewed

File without changes

{ext-torch → torch-ext}/torch_binding.cpp RENAMED Viewed

File without changes

{ext-torch → torch-ext}/torch_binding.h RENAMED Viewed

File without changes